Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
RED-PIM: Reducing Data Movement for Transformers using Processing-in-Memory
Zahra Yousefijamarani, Alaa Alameldeen
Transformers are widely used across many domains, including natural language processing, computer vision, web search, and DNA sequence analysis. Given their broad applicability, im…
cs.LG2025
MEPIC: Memory Efficient Position Independent Caching for LLM Serving
Qian Wang, Zahra Yousefijamarani, Morgan Lindsay Heisler +8
Modern LLM applications such as deep-research assistants, coding agents, and Retrieval-Augmented Generation (RAG) systems, repeatedly process long prompt histories containing share…